Plugins

Pauses the agent right before it sends the next model request of a tool round while keeping the composer usable: a bare Enter or the resume button lets it continue, and text typed meanwhile is sent along as a steering message; the pause never interrupts an in-flight API call and the model does not notice it.

Connects Qoder subscriptions to DeepSeek Harness, supporting Global and China regions, multimodal input, and tool calls.

omdsh: a keyboard-first DeepSeek TUI coding agent on the DeepSeek Harness runtime

Reference workspace files, DSH sessions, and historical ChatGPT, Claude, Gemini, DeepSeek, Grok, and Kimi conversations from the unified DSH @ menu.

Two-way iMessage channel for DeepSeek Harness over Photon: sender allowlisting, session commands, in-chat approvals and questions, and a Settings page for device authorization and hosted-line setup.

Two-phase agent preset for DeepSeek V4 Pro: the first request sees only bash+read (Minimal-aligned bootstrap), then the full Standard tool catalog after the first tool call or reply; ships as an installer bundle plus a manual preset directory.

DeepSeek Harness bundle registering one skill that turns long-form production (academic papers, industry analysis, business commentary) into a 9-role pipeline: T1 literature / T2 data / T3 case scouts running in parallel, T4 analyst, T5 writer, T6 critical companion, T7 auditor, T8 finalizer run by the coordinator, T9 peer reviewer — across 6 phases with triangular evidence verification, a 26-check M-gate (25 scripted checks plus one human checkpoint), a G0-G16 audit including a Chinese AI-trace gate, peer-review scoring with journal matching, and 4 human checkpoints. Installs with `dsh plugin add lunheng-article-pipeline` (package.json#dsh.bundle.patch plus a lib/index.js entry that registers the skill); ships role cards for T1-T9, templates and 36 zero-dependency verification scripts, with five-language READMEs.

Image generation and image reading for DSH: an Images page in the sidebar, labelled 图像 in Chinese (one row per model, 10 ratios, 1K–4K sizes, a contact sheet with detail cards, zoom, reuse and delete), three preset providers plus custom endpoints — one needs no key at all — and a vision-review skill. A pasted key is written to ~/.dsh/secrets/media-tools.env (mode 600) and only sent to the provider you picked. The page follows the harness language (Chinese or English). Requires Python 3.9+ (generation runs through scripts/generate.py); the page needs desktop DSH 0.2.1+.

Turns local markdown and text documents into a queryable knowledge base with hybrid semantic and keyword search, citation verification, and source injection.

Toy Control Protocol for DSH

Auto mode for DeepSeek Harness (dsh): an Auto entry in the Permissions selector whose approval prompts are answered by OpenGuardrails policy instead of a human — plus the full OGR guard engine underneath. No core changes.

Automatic conversation distillation: background subagent reflection + skill create/update.

Ultra-lean coding preset for DSH that eliminates orchestration overhead and pre-action chatter for surgical edits and fast tool execution.

Adds image_generate and image_library tools that pick reference images from four local libraries (characters, outfits, scenes, props), expand situation, expression, pose, shot and light keyword presets into the prompt, and call the 65535 async task API or any OpenAI-compatible images API, showing the result in the conversation; a settings page manages the libraries and turns an uploaded image or a text description into a three-view reference sheet. With dsh-daily-schedule installed, an image without a specified outfit uses what the character is wearing in the current schedule entry.

QQ channel for DeepSeek Harness over OneBot 11 / NapCat: keeps one fixed persona across sessions with long-term memory, answers in group and private chats, sends stickers and voice replies, and ships a local web console that shows what the bot is doing. Persona and memory files are yours to write — the repository only ships examples.

Hosts the WorkBuddy2API gateway in DSH with a native panel, a separately updatable kernel, and outbound fingerprint alignment with WorkBuddy Desktop 5.9.2.

DeepSeek Harness plugin for dsh-baton: adding it is the whole install. Switched on, it registers the dsh-baton MCP server for Claude Code and Codex, then takes the baton over a local, owner-only control socket, runs it in a specific session through the ho

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT): 76 skills, 49 agents, hook bridge.

Native interactive answers, editable cards and on-demand UI skills for DSH.

MCP management page in DSH Settings: list, enable/disable, restart and delete MCP servers, edit them in form or JSON mode, expand a server to see the tools it registers, paste-import MCP configs from 14 tools (Claude Code, Cursor, Codex, VS Code and more) in one go, and bind a server to project directories so only sessions working inside them can see or call its tools.

Plugin health checks (manifest/patch format/build pitfalls/hub status).

AI image and video studio as a floating DSH panel, so creation runs alongside the conversation instead of replacing it: text-to-image, image-to-image and multi-image composition at 1K-4K across eight aspect ratios; text-to-video and image-to-video with first-frame control at 4-12 seconds; short-drama mode that imports a script (.txt/.md/.json), breaks it into storyboard shots for preview and batch generation; and a prompt-expert workspace. Zero runtime dependencies.

TinyFish-backed web search provider for the built-in web_search tool: each search is one GET to the TinyFish Search API, no model call.

While vibe coding, save an answer you may need later, use Side Chat for a question that suddenly comes up, or open a related conversation for deeper work without losing focus on the current task.